Data processing device, electronic equipment and data processing method

A data processing device and data processing technology, which are applied in the field of data processing, can solve the problem that the convolution operation device is difficult to meet the accuracy requirements of a deep convolutional neural network, and achieve the effect of improving the accuracy

Pending Publication Date: 2021-04-09
SZ DJI TECH CO LTD
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides a data processing device, electronic equipment and data processing method to solve the technical problem that the convolution operation device in the prior art is difficult to meet the precision requirements of the deep convolutional neural network

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Data processing device, electronic equipment and data processing method
  • Data processing device, electronic equipment and data processing method
  • Data processing device, electronic equipment and data processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Embodiment 1 of the present invention provides a data processing device. image 3 It is a schematic structural diagram of a data processing device provided in Embodiment 1 of the present invention. Such as image 3 As shown, the data processing device in this embodiment may include:

[0058] The input module 1 is used to obtain an input eigenvalue matrix and an n-bit or 2n-bit weight value matrix, where n is a positive integer;

[0059] The calculation module 2 is used to perform convolution operation on the input eigenvalue matrix and the n-bit or 2n-bit weight value matrix to obtain the output eigenvalue matrix;

[0060] An output module 3, configured to output the output eigenvalue matrix.

[0061] Specifically, the input module 1 may be connected to a memory or other modules for obtaining an input feature value matrix and a weight value matrix to be subjected to convolution operations. Optionally, the connection described in each embodiment of the present invent...

Embodiment 2

[0079] Embodiment 2 of the present invention provides a data processing device. In this embodiment, on the basis of the technical solutions provided in the above embodiments, the convolution operation is realized through a systolic array, an accumulator array, and the like. Figure 5 It is a schematic structural diagram of a data processing device provided in Embodiment 2 of the present invention. Such as Figure 5 As shown, the data processing device in this embodiment may include:

[0080] The input module is used to obtain an n-bit or 2n-bit weight value matrix and an n-bit or 2n-bit input eigenvalue matrix; the input module may specifically include a weight value loading module 11 and an input eigenvalue loading module 12, and the weight value loading Module 11 is used to obtain n-bit or 2n-bit weight value matrix, and input eigenvalue loading module 12 is used to obtain n-bit or 2n-bit input eigenvalue matrix;

[0081] Calculation module 2, configured to perform convol...

Embodiment 3

[0119] Embodiment 3 of the present invention provides a data processing device. This embodiment provides a specific implementation solution of the pulsation unit and the accumulator based on the technical solutions provided by the above embodiments. The overall structural diagram of the data processing device in this embodiment can be found in Figure 5 . Figure 6 It is a schematic structural diagram of a pulse unit in a data processing device provided by Embodiment 3 of the present invention. Figure 7 It is a schematic structural diagram of an accumulator in a data processing device provided by Embodiment 3 of the present invention.

[0120] Such as Figure 6 As shown, the pulsation unit 21 may include:

[0121] Weight value register 211, used for storing weight value;

[0122] Input characteristic value register 212, used for storing input characteristic value;

[0123]The multiplication circuit 213 can be respectively connected to the weight value register 211 and t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a data processing device, electronic equipment and a data processing method, and the device comprises an input module (1) which is used for obtaining an input feature value matrix and an n-bit or 2n-bit weight value matrix; a calculation module (2) used for carrying out convolution operation on the input feature value matrix and the n-bit or 2n-bit weight value matrix to obtain an output feature value matrix; an output module (3) used for outputting the output feature value matrix, wherein n is a positive integer. Convolution operation of data of two lengths can be realized, the precision of the deep convolutional neural network is improved, and the design requirements of different deep convolutional neural networks are met.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of data processing, and in particular, to a data processing device, electronic equipment, and a data processing method. Background technique [0002] A deep convolutional neural network is a machine learning algorithm that is widely used in computer vision tasks such as object recognition, object detection, and semantic segmentation of images. [0003] Most of the operations of the deep convolutional neural network are convolution operations. Designing a dedicated hardware circuit to accelerate the convolution operation of the convolutional layer can greatly reduce the calculation time of the deep convolutional neural network. The operand of the existing convolution operation device only supports fixed-point numbers of one width, such as 8bits fixed-point numbers, so it cannot handle the data of deep convolutional neural networks with higher precision requirements, and it is difficu...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/063G06N3/04G06F17/15G06F7/544
CPCG06N3/063G06F17/15G06F7/5443G06N3/045
Inventor 杨康韩峰
Owner SZ DJI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products